This repo contains codes for RAG using docling on colab notebook with langchain, milvus, huggingface embedding model and LLM

An end-to-end tweet sentiment classification pipeline built on Sentiment140 — from preprocessing and vectorization (BoW/TF-IDF) to Qwen3 embeddings, model training, and full evaluation . Fast experiments, clean workflow, and ready for extension into a deployed app.

🧠 ML-Article-Classifier is a modular Python project for classifying articles using advanced NLP techniques. It features sentence embeddings, clustering, and classification utilities, with Jupyter notebook demos, extensible helper functions, and best practices for research and production use.

Notebooks to train and evaluate Amharic Text Embedding Models based on BERT and RoBERTa for Passage Retrieval

Jupyter Notebook illustrates and compares different approaches to sentence similarity scoring.

AI-powered Q&A for resumes using RAG and GPT-4o mini. CLI & Colab notebook included.

Retrieval-Augmented Generation demo: Webpage → Sentence-Transformer embeddings → ChromaDB → Gemini 2.5 Flash (LangChain). Local embeddings, reproducible notebook and demo code.

This repository is dedicated to exploring and implementing vector-based retrieval methods and reranking algorithms. It includes Jupyter notebooks with practical examples and code snippets that demonstrate how these techniques can be applied for efficient information retrieval in various datasets.

This repository is dedicated to exploring and implementing vector-based retrieval methods and reranking algorithms. It includes Jupyter notebooks with practical examples and code snippets that demonstrate how these techniques can be applied for efficient information retrieval in various datasets.